bigmorning
/

whisper_new_split_ch_08__0005

Automatic Speech Recognition

generated_from_keras_callback

Inference Endpoints

Model card Files Files and versions Community

bigmorning commited on Aug 10, 2023

Commit

d71e100

•

1 Parent(s): 3dc4eda

Upload TFWhisperForConditionalGeneration

Files changed (2) hide show

README.md +11 -11
tf_model.h5 +1 -1

README.md CHANGED Viewed

@@ -15,12 +15,12 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.5253
-- Train Accuracy: 0.0624
-- Train Wermet: 3.4109
-- Validation Loss: 1.4444
-- Validation Accuracy: 0.0400
-- Validation Wermet: 9.4755
 - Epoch: 4
 ## Model description
@@ -47,11 +47,11 @@ The following hyperparameters were used during training:
 | Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
 |:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
-| 2.3877     | 0.0442         | 1.0815       | 1.8406          | 0.0334              | 4.7983            | 0     |
-| 1.7865     | 0.0557         | 1.3855       | 1.6832          | 0.0357              | 5.7831            | 1     |
-| 1.6642     | 0.0589         | 2.5519       | 1.6045          | 0.0371              | 8.4362            | 2     |
-| 1.5873     | 0.0608         | 3.0818       | 1.5454          | 0.0381              | 10.0064           | 3     |
-| 1.5253     | 0.0624         | 3.4109       | 1.4444          | 0.0400              | 9.4755            | 4     |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 1.8240
+- Train Accuracy: 0.0439
+- Train Wermet: 4.6041
+- Validation Loss: 1.6213
+- Validation Accuracy: 0.0308
+- Validation Wermet: 12.0288
 - Epoch: 4
 ## Model description
 | Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
 |:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
+| 2.9164     | 0.0249         | 6.7624       | 2.3005          | 0.0222              | 17.3950           | 0     |
+| 2.2801     | 0.0354         | 6.3518       | 2.0871          | 0.0247              | 13.2620           | 1     |
+| 2.0950     | 0.0388         | 5.1467       | 1.9468          | 0.0263              | 12.7130           | 2     |
+| 1.9681     | 0.0411         | 4.7586       | 1.8190          | 0.0281              | 13.0904           | 3     |
+| 1.8240     | 0.0439         | 4.6041       | 1.6213          | 0.0308              | 12.0288           | 4     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d40b5d14ec25fad86cbb04ff497f77e26723b014c3fdca66fac62522e6b5d9
 size 151253960

 version https://git-lfs.github.com/spec/v1
+oid sha256:4e9db2c630c273adbb4ebac35134165d6786e6f641950ba38a3922dd5b87663a
 size 151253960